▶ code
▼ output
▶ uv-logs
|
Cell: combine | 4.45s
|
Raw
# /// script
# requires-python = ">=3.10"
# dependencies = [
# "numpy",
# "torch==2.8.0",
# "kernels-benchmark-tools",
# "matplotlib",
# ]
#
# [tool.uv.sources]
# kernels-benchmark-tools = { path = "../../../../../tools", editable = true }
# ///
from kernels_benchmark_tools.core.visuals import generate_combined_results
# Map display names to uvnote environment variables
cache_env_map = {
# "PyTorch OpenAI MoE": "UVNOTE_FILE_TORCH_OPENAI_MOE_BENCHMARK",
"Binned PyTorch": "UVNOTE_FILE_BINNED_TORCH_BENCHMARK",
"GptOssExperts": "UVNOTE_FILE_GPT_OSS_MOE_BENCHMARK",
}
# Generate combined results with visualization
generate_combined_results(
cache_env_map=cache_env_map,
output_filename="openai_moe.jsonl",
svg_filename="latency.svg"
)
======================================================================
LOADING BENCHMARK DATA
======================================================================
✓ Binned PyTorch : /__w/kernels-benchmarks/kernels-benchmarks/benches/openai_moe/impls/.uvnote/cache/fd01907ce582015b5dd52e56081cc8e2a21813f73271b422308d60a8ab9391af
✓ GptOssExperts : /__w/kernels-benchmarks/kernels-benchmarks/benches/openai_moe/impls/.uvnote/cache/002e3e7d42f2dbf6d5e5216db57e56aa649bc6ac59ce4131ce80c5849e52482b
✓ Found Binned PyTorch
Path: /__w/kernels-benchmarks/kernels-benchmarks/benches/openai_moe/impls/.uvnote/cache/fd01907ce582015b5dd52e56081cc8e2a21813f73271b422308d60a8ab9391af/openai_moe.jsonl
✓ Found GptOssExperts
Path: /__w/kernels-benchmarks/kernels-benchmarks/benches/openai_moe/impls/.uvnote/cache/002e3e7d42f2dbf6d5e5216db57e56aa649bc6ac59ce4131ce80c5849e52482b/openai_moe.jsonl
======================================================================
Summary: 2 found, 0 skipped, 0 missing
======================================================================
COMBINED BENCHMARK SUMMARY
impl wl p50(ms) ok
binned_torch cuda_B1_S1024_E2 367.98 True
binned_torch cuda_B1_S1024_E4 396.30 True
binned_torch cuda_B1_S512_E2 154.35 True
binned_torch cuda_B1_S512_E4 195.55 True
binned_torch cuda_B4_S1024_E2 1510.09 True
binned_torch cuda_B4_S1024_E4 1618.05 True
binned_torch cuda_B4_S512_E2 733.47 True
binned_torch cuda_B4_S512_E4 787.61 True
gpt_oss_experts cuda_B1_S1024_E2 3.87 True
gpt_oss_experts cuda_B1_S1024_E4 5.34 True
gpt_oss_experts cuda_B1_S512_E2 2.66 True
gpt_oss_experts cuda_B1_S512_E4 3.95 True
gpt_oss_experts cuda_B4_S1024_E2 13.39 True
gpt_oss_experts cuda_B4_S1024_E4 13.41 True
gpt_oss_experts cuda_B4_S512_E2 6.80 True
gpt_oss_experts cuda_B4_S512_E4 7.53 True
GENERATING COMBINED VISUALIZATION
Loaded 16 records
✓ Visualization saved as latency.svg
Saved latency.png
✓ Visualization saved as latency.svg
✓ SVG visualization ready!
ANALYSIS COMPLETE
Total implementations analyzed: 2
Implementations included:
✓ Binned PyTorch
✓ GptOssExperts
▶ UV Install Logs